Intelligent Interface for Automation Multitasking

Abstract

Techniques for intelligently managing task automation across multiple tasks and multiple automated assistants are provided. In one aspect, an intelligent multitasking system includes: a context manager configured to use human-centric input data to determine a context of a user; an intent mapper configured to map human communication to automated task intents; and an interruption manager configured to schedule automated tasks for performance by automated assistants based on the context of the user and the automated task intents. The context manager can be hosted on a cloud having MQTT clients (e.g., IoT sensors) and an MQTT broker. The intent mapper can include a human-machine software communication interface that identifies verbal and/or non-verbal communications. A method for intelligent multitasking is also provided.

What is claimed is: 
     
         1 . An intelligent multitasking system, comprising:
 a context manager configured to use human-centric input data to determine a context of a user;   an intent mapper configured to map human communication to automated task intents; and   an interruption manager configured to schedule automated tasks for performance by automated assistants based on the context of the user and the automated task intents.   
     
     
         2 . The intelligent multitasking system of  claim 1 , wherein the human-centric input data is selected from the group consisting of: human-computer interactions, software application logs, input from biometric sensors, machine learning, and combinations thereof. 
     
     
         3 . The intelligent multitasking system of  claim 2 , wherein the context manager is further configured to create context profiles which take into account factors selected from the group consisting of: day of the week, date, time, scheduled events, break time, free time, recurring events, deadlines, past behaviors, biometric data, and combinations thereof. 
     
     
         4 . The intelligent multitasking system of  claim 1 , wherein the human-centric input data is obtained using sensors which are part of a computing device of the user. 
     
     
         5 . The intelligent multitasking system of  claim 4 , wherein the sensors comprise biometric sensors. 
     
     
         6 . The intelligent multitasking system of  claim 1 , wherein a mode of the human communication is selected from the group consisting of: text, voice, gesture, and combinations thereof. 
     
     
         7 . An intelligent multitasking system, comprising:
 a context manager configured to use human-centric input data to determine a context of a user, wherein the context manager comprises MQ Telemetry Transport (MQTT) clients, and an MQTT broker for receiving messages from the MQTT clients, and routing the messages to destination modules in the context manager;   an intent mapper configured to map human communication to automated task intents, wherein the intent mapper comprises a human-machine software communication interface that identifies the human communication, and wherein the human communication comprises verbal communications, non-verbal communications, or both; and   an interruption manager configured to schedule automated tasks for performance by automated assistants based on the context of the user and the automated task intents.   
     
     
         8 . The intelligent multitasking system of  claim 7 , wherein the human-centric input data is selected from the group consisting of: human-computer interactions, software application logs, input from biometric sensors, machine learning, and combinations thereof. 
     
     
         9 . The intelligent multitasking system of  claim 8 , wherein the context manager is further configured to create context profiles which take into account factors selected from the group consisting of: day of the week, date, time, scheduled events, break time, free time, recurring events, deadlines, past behaviors, biometric data, and combinations thereof. 
     
     
         10 . The intelligent multitasking system of  claim 7 , wherein the MQTT clients comprise sensors which are part of a computing device of the user. 
     
     
         11 . The intelligent multitasking system of  claim 10 , wherein the sensors comprise biometric sensors. 
     
     
         12 . The intelligent multitasking system of  claim 7 , wherein the destination modules comprise:
 a database of previous human-computer interactions; and   a modified machine learning regression algorithm.   
     
     
         13 . The intelligent multitasking system of  claim 7 , wherein a mode of the human communication is selected from the group consisting of: text, voice, gesture, and combinations thereof. 
     
     
         14 . The intelligent multitasking system of  claim 7 , wherein the intent mapper comprises:
 a word analyzer configured to convert the verbal communications into utterance vectors;   a non-word analyzer configured to convert the non-verbal communications into the utterance vectors; and   an intent analyzer configured to correlate the utterance vectors to matching utterance vectors related to a specific intent of the user.   
     
     
         15 . The intelligent multitasking system of  claim 14 , wherein the intent mapper further comprises:
 an intent tagger configured to tag variations of the human communication that convey a same intent.   
     
     
         16 . The intelligent multitasking system of  claim 7 , wherein the interruption manager comprises:
 a slot manager configured to determine time slots in a schedule of the user to put the automated assistants in order to perform the automated tasks; and   an interruption scheduler configured to decide whether the time slots are proper times to interrupt the user.   
     
     
         17 . A method for intelligent multitasking, the method comprising:
 using human-centric input data to determine a context of a user, wherein the human-centric input data is selected from the group consisting of: human-computer interactions, software application logs, input from biometric sensors, machine learning, and combinations thereof;   mapping human communication to automated task intents, wherein the human communication comprises verbal communications, non-verbal communications, or both, and wherein a mode of the human communication is selected from the group consisting of: text, voice, gesture, and combinations thereof; and   scheduling automated tasks for performance by automated assistants based on the context of the user and the automated task intents.   
     
     
         18 . The method of  claim 17 , further comprising:
 converting the verbal communications into utterance vectors;   converting the non-verbal communications into the utterance vectors; and   correlating the utterance vectors to matching utterance vectors related to a specific intent of the user.   
     
     
         19 . The method of  claim 18 , further comprising:
 tagging variations of the human communication that convey a same intent.   
     
     
         20 . The method of  claim 17 , further comprising:
 determining time slots in a schedule of the user to put the automated assistants in order to perform the automated tasks; and   deciding whether the time slots are proper times to interrupt the user.